Metering device clock error trend prediction method based on social perception

Abstract

The invention discloses a metering device clock error trend prediction method based on social perception, and relates to the field of electric power operation and maintenance. Existing work can only solve the clock error problem of a specific scene and is not universal enough. According to the method, a time sequence evolution gene model is adopted, an ammeter clock error is divided into a plurality of sub-sequences on a certain window, the model can analyze the error change characteristics of the window sub-sequences, and the sub-sequences with similar distribution are divided into one blockthrough a classifier of the model; genes for generating the subsequence distribution characteristics are mined through a generative adversarial network; the genes of the sub-sequences in history are combined, the evolution process of the sub-sequences is analyzed through a recurrent neural network, the evolution mode of the sub-sequences is analyzed and the future clock error trend of the sub-sequences is predicted. The technical scheme is not limited to specific devices and reasons causing errors, and can adapt to different scenes, so that a more universal scheme is provided, and the generalized clock error problem of the electric energy device is solved.

Description

technical field [0001] The invention relates to the field of electric power operation and maintenance, in particular to a method for predicting clock error trends of metering devices based on social perception. Background technique [0002] The normal and stable operation of electric energy metering equipment affects the development of power grid companies and the economic benefits of their operations. Among them, the clock is one of the basic components of the metering device, and its accuracy is directly related to whether the metering device can accurately measure data in different periods. However, due to many reasons such as inaccurate clock synchronization signals, device crystal oscillator clock frequency not meeting the requirements of regulations, communication delays, device response delays, and different implementation methods of time calibration software, it is inevitable that the time of the energy metering device will be different from the standard time. Devia...

AI Technical Summary

Problems solved by technology

However, due to many reasons such as inaccurate clock synchronization signals, device crystal oscillator clock frequency not meeting the requirements of regulations, communication delays, device response delays, and different implementation methods of time calibration software, it is inevitable that the time of the energy metering device will be different from the standard time. Deviation occurred

[0003]However, the existing works can only solve the clock error problem in specific scenarios, and are not generalized enough

When the metering device is replaced or the device has a clock skew due to other more different problems, the previous precautions cannot be continued

The root cause of these problems is that the existing work is often carried out from specific reasons such as the design of the metering device and the cause of the error, but lacks the full analysis and utilization of the massive historical error records

Images